language benchmark
CoVoST2 Leaderboard
CoVoST2 is a multilingual speech translation corpus covering translations from 21 languages into English and from English into 15 languages.
Updated Sep 5, 2026
Models4
Model coverage4
MetricScore
EvidenceB
CoVoST2 Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAM Nova 2 OmniAmazon | Score40.70% | Percentile100.00% | Participants4 | EvidenceC | Evaluated |
| Rank02 | ModelGO | Score39.20% | Percentile66.67% | Participants4 | EvidenceC | Evaluated |
| Rank03 | ModelGO | Score38.50% | Percentile33.33% | Participants4 | EvidenceC | Evaluated |
| Rank04 | ModelGO | Score38.40% | Percentile0.00% | Participants4 | EvidenceC | Evaluated |
CoVoST2 Highlights
The leading models and scores on this benchmark.
CoVoST2 Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for CoVoST2
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is CoVoST2?
What CoVoST2 measures and how its scores work.
CoVoST2 is a large-scale multilingual speech translation corpus derived from Common Voice, containing 2,880 hours of speech with 78K speakers for speech translation research.
It reports a Score as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- CoVoST2
- Modality
- audio
- Primary category
- language
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about CoVoST2.
Which model scores highest on CoVoST2?
Nova 2 Omni is currently ranked first with 40.70%.
What are the top three models on CoVoST2?
The current leaders are Nova 2 Omni (40.70%), Gemini 2.0 Flash (39.20%), and Gemma 4 12B (38.50%).
Which CoVoST2 model has the lowest official input price?
No matched official input price is currently available.
Which models are fastest among CoVoST2 results?
The fastest matched records are Gemini 2.0 Flash (183.00 tok/s via Google) and Gemini 2.0 Flash-Lite (85.00 tok/s via Google).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.